CN117809458A - Real-time assessment method and system for traffic accident risk - Google Patents
Real-time assessment method and system for traffic accident risk Download PDFInfo
- Publication number
- CN117809458A CN117809458A CN202410231340.9A CN202410231340A CN117809458A CN 117809458 A CN117809458 A CN 117809458A CN 202410231340 A CN202410231340 A CN 202410231340A CN 117809458 A CN117809458 A CN 117809458A
- Authority
- CN
- China
- Prior art keywords
- traffic
- risk
- conflict
- collision
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 56
- 238000012502 risk assessment Methods 0.000 claims abstract description 31
- 238000012163 sequencing technique Methods 0.000 claims abstract description 12
- 238000013210 evaluation model Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 238000007476 Maximum Likelihood Methods 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 230000008030 elimination Effects 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000003657 Likelihood-ratio test Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000013211 curve analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a real-time assessment method and a real-time assessment system for traffic accident risks, and relates to the technical field of traffic collision. The method comprises the following steps: acquiring vehicle data and road data of a road section to be evaluated, and analyzing traffic flow characteristics according to the vehicle data and the road data; determining the traffic safety state of the road section according to the traffic conflict condition of the road section to be evaluated; calculating traffic conflict risk evaluation indexes according to traffic flow characteristics, calculating the correlation of the traffic conflict risk evaluation indexes, further calculating the importance of the indexes, sequencing, and obtaining an evaluation index set according to sequencing results; constructing a traffic risk assessment model by using the evaluation index set and the road traffic safety state; and processing the real-time data of the road section to be evaluated by using the traffic risk evaluation model to obtain a risk evaluation result. The invention realizes real-time and accurate assessment of the risk probability of the traffic accident.
Description
Technical Field
The invention relates to the technical field of traffic conflict, in particular to a real-time assessment method and a real-time assessment system for traffic accident risks.
Background
After an accident occurs on an urban road, the vehicles in different running states of different lanes around the accident vehicle are seriously interfered with each other, so that the road condition is more complex than other areas of the road, the interlinked collision phenomenon is very easy to occur, the accident form is further aggravated, larger casualties and losses are caused, and finally, the passing efficiency and the operation safety of the whole urban road network are influenced. Current research on collision risk is mainly focused on single car collision risk, ignoring interactions between collision vehicles and risk assessment on road section level. In addition, accident data are relatively difficult to obtain, the sample size is small, the real-time performance is poor, and the phenomenon of unbalanced data easily occurs in the modeling process, so that the real-time performance and the accuracy of the assessment of the traffic accident risk in the prior art are lacked.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a real-time assessment method and a real-time assessment system for traffic accident risks, wherein three indexes of the number of conflicts, the severity of the conflicts and the number of related vehicles in the conflicts are selected based on a traffic conflict technology to measure the road section risks, a risk assessment index set is constructed by calculating the selected indexes from the three aspects of speed, flow and lane change, and a road section risk identification model is constructed based on a binary logic model, so that real-time and accurate assessment of the road section traffic accident risk probability is realized.
In order to achieve the above object, the present invention is realized by the following technical scheme:
the first aspect of the invention provides a real-time assessment method for traffic accident risks, which comprises the following steps:
acquiring vehicle data and road data of a road section to be evaluated, and analyzing traffic flow characteristics according to the vehicle data and the road data;
determining the traffic safety state of the road section according to the traffic conflict condition of the road section to be evaluated;
calculating traffic conflict risk evaluation indexes according to traffic flow characteristics, calculating the correlation of the traffic conflict risk evaluation indexes, further calculating the importance of the indexes, sequencing, and obtaining an evaluation index set according to sequencing results;
constructing a traffic risk assessment model by using the evaluation index set and the road traffic safety state;
and processing the real-time data of the road section to be evaluated by using the traffic risk evaluation model to obtain a risk evaluation result.
Further, the traffic flow characteristic analysis is performed by considering the running characteristics and lane changing behavior of the vehicle and combining the traffic flow.
Further, the specific steps of determining the road traffic safety state according to the road traffic conflict condition to be evaluated are as follows:
calculating a collision phenomenon safety value according to the expanded ranging collision algorithm;
calculating the traffic conflict severity according to the conflict phenomenon threshold;
calculating traffic conflict aggregation according to the number of vehicles with traffic conflict in the selected time window;
and determining the traffic safety state of the road section by using a clustering algorithm in combination with the traffic conflict severity and the traffic conflict aggregation.
Further, the specific steps of calculating the collision phenomenon safety value according to the extended ranging collision algorithm are as follows:
determining a conflict index according to the conflict phenomenon influence factors;
constructing a collision time deduction model of the vehicle collision index in the interweaved area according to the collision index;
and calculating a collision phenomenon safety value by using the collision time deduction model of the vehicle collision indexes in the interweaving area.
Further, traffic conflict severity includes severe conflicts, general conflicts, and minor conflicts.
Further, traffic safety conditions include risky and risky.
Further, calculating traffic conflict risk evaluation indexes according to traffic flow characteristics, calculating the correlation of the traffic conflict risk evaluation indexes, further calculating the importance of the indexes, and sequencing, wherein the specific steps of obtaining an evaluation index set according to the sequencing result are as follows:
determining a traffic conflict risk evaluation index according to the traffic flow characteristic analysis result, and extracting relevant traffic parameters of the traffic conflict risk evaluation index;
determining a correlation coefficient according to the traffic parameters, and performing correlation calculation of traffic conflict risk evaluation indexes;
and ordering the importance degree of the traffic conflict risk evaluation indexes by using a recursive feature elimination algorithm to obtain an evaluation index set.
Further, a traffic risk assessment model is established by using the Logit model, and parameter estimation is carried out on the traffic risk assessment model by using a maximum likelihood method.
Further, the likelihood ratio is used for carrying out effect test on the traffic risk assessment model.
The second aspect of the present invention provides a real-time traffic accident risk assessment system, comprising:
the data acquisition module is configured to acquire vehicle data and road data of a road section to be evaluated, and analyze traffic flow characteristics according to the vehicle data and the road data;
the risk judging module is configured to determine the road traffic safety state according to the road traffic conflict condition to be evaluated;
the index screening module is configured to calculate traffic conflict risk evaluation indexes according to traffic flow characteristics, calculate the correlation of the traffic conflict risk evaluation indexes, further calculate index importance for sorting, and obtain an evaluation index set according to sorting results;
the model construction module is configured to construct a traffic risk assessment model by using the evaluation index set and the road traffic safety state;
the risk assessment module is configured to process real-time data of the road section to be assessed by using the traffic risk assessment model to obtain a risk assessment result.
The one or more of the above technical solutions have the following beneficial effects:
the invention discloses a real-time assessment method and a real-time assessment system for traffic accident risk, which are used for calculating road section traffic conflict conditions by selecting an expanded ranging collision algorithm (extend time to collision, ETTC) based on high-precision vehicle track data and carrying out risk calibration on road sections based on the traffic conflict quantity, traffic conflict severity and conflict vehicle number in unit time of the road sections; considering the running state of the road traffic flow, selecting indexes from three aspects of speed characteristics, road changing behaviors and traffic flow to construct an interweaving region risk evaluation index set, finally establishing a road risk identification model based on a binary logic model, and completing model parameter estimation by using a maximum likelihood method to realize real-time and accurate evaluation of the road traffic accident risk probability.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a real-time assessment method for traffic accident risk in a first embodiment of the invention;
FIG. 2 is a schematic diagram of a collision time derivation model of a vehicle collision index in an interlaced region according to an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof;
embodiment one:
the first embodiment of the invention provides a real-time assessment method for traffic accident risk, as shown in fig. 1, comprising the following steps:
s1: and acquiring vehicle data and road data of the road section to be evaluated, and analyzing traffic flow characteristics according to the vehicle data and the road data.
S2: and determining the traffic safety state of the road section according to the traffic conflict condition of the road section to be evaluated.
S3: and calculating traffic conflict risk evaluation indexes according to traffic flow characteristics, calculating the correlation of the traffic conflict risk evaluation indexes, further calculating the importance of the indexes, sequencing, and obtaining an evaluation index set according to the sequencing result.
S4: and constructing a traffic risk assessment model by using the evaluation index set and the road traffic safety state.
S5: and processing the real-time data of the road section to be evaluated by using the traffic risk evaluation model to obtain a risk evaluation result.
In S1, the traffic flow characteristic analysis is carried out by considering the running characteristics of the vehicle and the lane changing behavior and combining the traffic flow.
In the present embodiment, the vehicle running characteristic is represented as the running speed of the vehicle.
The judging process of the lane change behavior is as follows: firstly, the lane lines are calibrated, then, which lane the vehicle belongs to is judged in real time according to the position of the central point of the vehicle, and whether lane change behavior occurs or not is judged.
S2, determining the road section traffic safety state according to the road section traffic conflict condition to be evaluated comprises the following specific steps:
s2.1: and calculating a collision phenomenon safety value according to the extended ranging collision algorithm.
Considering the driving characteristics of the vehicle and the complex lane changing behavior, the embodiment selects Extended TTC (ETTC) to describe the traffic collision phenomenon of the vehicle on the road section, and compared with the TTC, the ETTC is more suitable for the general two-dimensional vehicle movement, i.e. can be used for describing the unconstrained traffic collision. The method comprises the following specific steps:
s2.1.1: and determining a conflict index ETTC according to the conflict phenomenon influence factors. Specifically, according to the traffic flow characteristic analysis result, the factors influencing the collision phenomenon include a vehicle position factor, a speed factor and a vehicle length factor.
S2.1.2: and constructing a collision time deduction model of the vehicle collision indexes in the interweaved area according to the collision indexes.
In a specific embodiment, as shown in fig. 2, it is assumed that the vehicle of the investigation region moves under an XY two-dimensional plane coordinate system in which the X-axis represents lateral displacement and the Y-axis represents longitudinal displacement, all in m. The speed, the position and the direction of the vehicle q and the vehicle h at any moment are arbitrary, so that collision at any angle can occur between the two vehicles, and the position and the speed coordinates of the vehicles are expressed in the form of vectors.
Assuming that the positional speed relationship between the following vehicle h and its preceding vehicle q is shown in fig. 2 at a certain time t, the ETTC between the two vehicles can be calculated by the following equation.
（1）。
In the method, in the process of the invention,ETTC value at t-time, < +.>,/>Centroid position coordinate vector of vehicle q and h at time t, respectively, < >>,/>Speed vectors of vehicles q and h at time t, respectively,/->，/>The vehicle length of the front vehicle q and the rear vehicle h.
S2.1.3: calculating collision phenomenon safety value by using collision time deduction model of vehicle collision index in interweaving area, namelyValues.
In the past, a fixed threshold value is generally used for judging whether traffic collision occurs to a vehicle, when the TTC value is smaller than the threshold value, the vehicle cannot make a risk avoidance decision in a corresponding time so as to avoid the traffic collision, and the vehicle is in a dangerous state at the moment, otherwise, the vehicle is in a safe state. Since the definition of ETTC is basically the same as that of TTC, the same threshold theory can be used to determine the vehicle safety state, and the threshold of TTC is usually 2 to 4 seconds, and the threshold varies according to the influence of factors such as traffic environment, driver, vehicle, etc. The present embodiment selects 4 seconds as the safety threshold and specifies a time step of calculating the ETTC of 1 second.
S2.2: and calculating the traffic conflict severity according to the conflict phenomenon threshold value. Traffic conflict severity includes severe conflicts, general conflicts, and minor conflicts. Specifically, the severity of traffic collisions is measured by the number of traffic collisions occurring within a selected time window and the average of ETTC values.
In a specific embodiment, when a traffic collision occurs on a road due to the driving habit of a driver and the influence of surrounding road conditions, the collision has a difference in severity, and may be generally classified into a serious collision, a general collision, and a slight collision. Early scholars research finds that the severity of the conflict is related to the possibility of accident, and the more serious the traffic conflict is, the more likely the traffic accident is happened, so that the conflict severity analysis is necessary for conflict samples collected by the research. The 85% bit cumulative frequency curve analysis method is commonly used for traffic conflict severity analysis and is a more widely used analysis method at present. In this embodiment, the 5s is used as a time interval, the statistical road traffic conflict sample is extracted, and the cumulative frequency 15%, 50% and 85% bit values are used as the discrimination thresholds for serious conflicts, general conflicts and slight conflicts.
S2.3: and calculating the traffic conflict aggregation according to the number of vehicles with traffic conflict in the selected time window.
The road traffic safety state can be timely and accurately judged, effective driving guidance information can be provided for a driver who is about to enter the road, so that a correct driving decision is made, and the road traffic conflict degree is prevented from being further increased, and the traffic flow running order of an interweaving area is prevented from being influenced. In the prior art, the evaluation and research on the whole safety state of the road are carried out by the number of traffic conflicts, but the influence caused by the severity and the aggregation of the conflicts is ignored. The observation of the traffic conflict video clips reveals that the influence of traffic conflicts caused by multiple vehicles on the overall safety of an interweaving area is far greater than that caused by two vehicles, the scope of the traffic conflicts is wider, and the traffic accidents are worse.
Thus, the present embodiment characterizes traffic conflict congregation for the investigation region in terms of the number of vehicles that are in traffic conflict within the selected time window.
S2.4: and determining the traffic safety state of the road section by using a clustering algorithm in combination with the traffic conflict severity and the traffic conflict aggregation.
In a specific embodiment, common distinguishing methods include gray clustering, K-means, density-based clustering (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) and the like, wherein the K-means algorithm has high convergence rate and strong model interpretation, can directly define the class number of the clusters, and is suitable for the cluster analysis of the known class number. In the embodiment, the K-means algorithm is finally selected for road safety sample calibration, the number of conflicts, the severity of the conflicts and the number of the conflicting vehicles are used as the input of the K-means algorithm, K is set to be 2, namely the road section traffic safety states are divided into two types: no risk and risk.
S3, calculating traffic conflict risk evaluation indexes according to traffic flow characteristics, calculating the correlation of the traffic conflict risk evaluation indexes, further calculating the importance of the indexes, and sequencing, wherein the specific steps of obtaining an evaluation index set according to the sequencing result are as follows:
s3.1: and determining a traffic conflict risk evaluation index according to the traffic flow characteristic analysis result, and extracting relevant traffic parameters of the traffic conflict risk evaluation index.
Specifically, indexes such as traffic volume, number of lane change vehicles, speed of vehicles entering a road section at the beginning, average speed of vehicles, extremely poor speed of vehicles and the like in a unit time window are determined according to traffic flow characteristic analysis results, relevant traffic parameters are extracted, meanwhile, influence of congestion conditions on road section risks is considered, and congestion indexes in the unit time window are further extracted to quantify the congestion state of the road section.
S3.2: and determining a correlation coefficient according to the traffic parameters, and calculating the correlation and importance of the traffic conflict risk evaluation index.
In a specific implementation manner, since the index selected in this embodiment is mostly related to speed and flow, there may be a correlation between variables to some extent, which affects the prediction effect of the model. In addition, too many variable indexes are selected, so that the training speed of the model is influenced to a certain extent. Therefore, in order to reduce the index variable system, the embodiment adopts Pearson (Pearson) correlation coefficient to analyze, and checks whether multiple collinearity exists between the selected variables. The Pearson correlation coefficient is also called the product difference correlation (or product moment correlation), assuming that there is、/>The calculation method of the two variables is the quotient of the covariance and the standard deviation between the two variables.
The Sample phase relation (Sample correlation coefficient) is written asThe calculation formula is shown in formula (2).
（2）。
In the method, in the process of the invention,for the sample correlation coefficient, +.>Is the number of samples; />，/>Is->Variable correspondence->An observation of the point;is->Average value of samples; />Is->Average value of samples.
Wherein, the value of r is between-1 and 1. The positive and negative of r represent positive correlation or negative correlation between two variables, and the absolute value of r represents the correlation strength between the two variables, and the closer the value is to 1 or-1, the stronger the correlation degree is, and conversely, the closer the value is to 0, the weaker the correlation degree is. When r takes on a value of 0, it indicates that the linearity between the two random variables is irrelevant.
S3.3: and ordering the importance degree of the traffic conflict risk evaluation indexes by using a recursive feature elimination algorithm to obtain an evaluation index set.
In one embodiment, to ensure accuracy of subsequent modeling, the feature variables that present multiple collineation problems should be removed. A generally straightforward approach is to delete feature variables that have a strong correlation, but this may delete variables that have a significant impact on the road risk status. Therefore, the embodiment adopts a recursive feature elimination algorithm to sort the importance of the feature variables, and removes the variables with lower importance from the two-to-two related variables. The recursive feature elimination algorithm (Recursive Feature Elimination, RFE) is a well-performing backward search feature screening method, belonging to one of the packing method feature selection algorithms. The core idea is to select the best (or worst) feature by repeatedly constructing a model (such as a support vector machine or regression model), select the selected feature, and continue repeating this process on the remaining features until all features have been traversed. The algorithm can select the variable which contributes the most to the dependent variable (road traffic running risk state) while screening the characteristics.
And S4, establishing a traffic risk assessment model by using the Logit model, and carrying out parameter estimation on the traffic risk assessment model by using a maximum likelihood method.
In a specific embodiment, the Logit model is a discrete selection model, and has the advantages of high solving speed and convenient application because of the explicit characteristics of the probability expression, and is widely applied to traffic accident analysis at present. In the embodiment, when predicting road risk identification, the dependent variable is defined as two kinds of variables, namely, whether a road section has risk (no risk is 0 and no risk is 1), so that a binary logic model is selected for modeling. Binary logic regression converts the 0, 1 value of the classification dependent variable into probability of taking its value, and converts the classification model into a linear function model, which can be expressed as the following formula.
（3），
（4）。
In the method, in the process of the invention,for probability->Is->Probability of risk occurrence of a section of the time window, +.>Is an intercept term;is a regression coefficient variable; />Is->Interpretation variable of the individual time window,/>For substitution into actual values in the binary logic model.
The core of the method is to estimate parameters of a logic model by using a common maximum likelihood estimation methodFrom all parameters->Find out the parameter which can generate the observation data with the highest probability +.>As a result of the estimation. Before applying the maximum likelihood estimation method, likelihood functions expressed as unknown model parameters by the probability of occurrence of road segment risks need to be established, and the specific deductions are as follows:
assume the firstThe probability of risk occurrence of a section of the time window is +.>The probability of risk-free occurrence of the road section under the same conditions is +.>. Thereby get->The probability of risk occurrence for each time window segment is equation (5).
（5）。
In the method, in the process of the invention,is->Probability of risk occurrence for each time window segment.
Since the samples of each time window are independent of each otherThe likelihood function for each time window is equation (6).
（6）。
Wherein,is a likelihood function.
Natural logarithmic change is carried out on two sides of the formulas (5) and (4), and the log likelihood value is calculatedEquation 7 is finally obtained.
（7）。
Finally, the intercept term of the log-likelihood function and the regression coefficient of the interpretation variable are respectively biased and led toEqual to 0, and finally obtaining the energy by iterative calculationMaximum overall parameters.
And then, carrying out effect test on the traffic risk assessment model by using likelihood ratio.
In a specific embodiment, a traffic risk assessment model established by likelihood ratio test assessment is introduced. The principle of likelihood ratio test is to evaluate the quality of fitting between different models by comparing the maximum likelihood values of the corresponding likelihood functions of the fitting models. The likelihood ratio test is divided into forward likelihood test and backward likelihood test, wherein the principle of the forward likelihood test is that each variable is tested to obtain Wald value and test probability Sig. And then substituting the test probability from low to high into the regression equation one by one to carry out iterative operation. The principle of backward likelihood test is that all independent variables are firstly incorporated into a model, then the independent variables are eliminated one by one based on probability results of likelihood ratio statistics based on maximum partial likelihood estimation, and a prediction model with optimal effect is obtained.
Embodiment two:
the second embodiment of the invention provides a real-time assessment system for traffic accident risk, which comprises:
the data acquisition module is configured to acquire vehicle data and road data of a road section to be evaluated, and analyze traffic flow characteristics according to the vehicle data and the road data;
the risk judging module is configured to determine the road traffic safety state according to the road traffic conflict condition to be evaluated;
the index screening module is configured to calculate traffic conflict risk evaluation indexes according to traffic flow characteristics, calculate the correlation of the traffic conflict risk evaluation indexes, further calculate index importance for sorting, and obtain an evaluation index set according to sorting results;
the model construction module is configured to construct a traffic risk assessment model by using the evaluation index set and the road traffic safety state;
the risk assessment module is configured to process real-time data of the road section to be assessed by using the traffic risk assessment model to obtain a risk assessment result.
The steps involved in the second embodiment correspond to those of the first embodiment of the method, and the detailed description of the second embodiment can be found in the related description section of the first embodiment.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. The real-time assessment method for the traffic accident risk is characterized by comprising the following steps of:
acquiring vehicle data and road data of a road section to be evaluated, and analyzing traffic flow characteristics according to the vehicle data and the road data;
determining the traffic safety state of the road section according to the traffic conflict condition of the road section to be evaluated;
calculating traffic conflict risk evaluation indexes according to traffic flow characteristics, calculating the correlation of the traffic conflict risk evaluation indexes, further calculating the importance of the indexes, sequencing, and obtaining an evaluation index set according to sequencing results;
constructing a traffic risk assessment model by using the evaluation index set and the road traffic safety state;
and processing the real-time data of the road section to be evaluated by using the traffic risk evaluation model to obtain a risk evaluation result.
2. The traffic accident risk real-time assessment method according to claim 1, wherein traffic flow characteristic analysis is performed in consideration of vehicle running characteristics and lane changing behavior in combination with traffic flow.
3. The traffic accident risk real-time assessment method according to claim 1, wherein the specific steps of determining the road traffic safety state according to the road traffic collision condition to be assessed are:
calculating a collision phenomenon safety value according to the expanded ranging collision algorithm;
calculating the traffic conflict severity according to the conflict phenomenon threshold;
calculating traffic conflict aggregation according to the number of vehicles with traffic conflict in the selected time window;
and determining the traffic safety state of the road section by using a clustering algorithm in combination with the traffic conflict severity and the traffic conflict aggregation.
4. The traffic accident risk real-time assessment method according to claim 3, wherein the specific steps of calculating the collision phenomenon safety value according to the extended ranging collision algorithm are:
determining a conflict index according to the conflict phenomenon influence factors;
constructing a collision time deduction model of the vehicle collision index in the interweaved area according to the collision index;
and calculating a collision phenomenon safety value by using the collision time deduction model of the vehicle collision indexes in the interweaving area.
5. The traffic accident risk real-time assessment method according to claim 3, wherein the traffic collision severity includes a serious collision, a general collision and a slight collision.
6. The traffic accident risk real-time assessment method according to claim 3, wherein the traffic safety status includes risky and risky.
7. The method for real-time assessment of traffic accident risk according to claim 1, wherein the specific steps of calculating traffic collision risk assessment indexes according to traffic flow characteristics, calculating the correlation of the traffic collision risk assessment indexes and further calculating the importance of the indexes for ranking, and obtaining the assessment index set according to the ranking result are as follows:
determining a traffic conflict risk evaluation index according to the traffic flow characteristic analysis result, and extracting relevant traffic parameters of the traffic conflict risk evaluation index;
determining a correlation coefficient according to the traffic parameters, and performing correlation calculation of traffic conflict risk evaluation indexes;
and ordering the importance degree of the traffic conflict risk evaluation indexes by using a recursive feature elimination algorithm to obtain an evaluation index set.
8. The traffic accident risk real-time assessment method according to claim 1, wherein a traffic risk assessment model is established by using a logic model, and parameter estimation is performed on the traffic risk assessment model by using a maximum likelihood method.
9. The traffic accident risk real-time assessment method according to claim 1, wherein the effect test is performed on the traffic risk assessment model using likelihood ratios.
10. A real-time assessment system for traffic accident risk, comprising:
the data acquisition module is configured to acquire vehicle data and road data of a road section to be evaluated, and analyze traffic flow characteristics according to the vehicle data and the road data;
the risk judging module is configured to determine the road traffic safety state according to the road traffic conflict condition to be evaluated;
the index screening module is configured to calculate traffic conflict risk evaluation indexes according to traffic flow characteristics, calculate the correlation of the traffic conflict risk evaluation indexes, further calculate index importance for sorting, and obtain an evaluation index set according to sorting results;
the model construction module is configured to construct a traffic risk assessment model by using the evaluation index set and the road traffic safety state;
the risk assessment module is configured to process real-time data of the road section to be assessed by using the traffic risk assessment model to obtain a risk assessment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410231340.9A CN117809458A (en) | 2024-03-01 | 2024-03-01 | Real-time assessment method and system for traffic accident risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410231340.9A CN117809458A (en) | 2024-03-01 | 2024-03-01 | Real-time assessment method and system for traffic accident risk |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117809458A true CN117809458A (en) | 2024-04-02 |
Family
ID=90422006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410231340.9A Pending CN117809458A (en) | 2024-03-01 | 2024-03-01 | Real-time assessment method and system for traffic accident risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117809458A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508392A (en) * | 2020-12-02 | 2021-03-16 | 云南省交通规划设计研究院有限公司 | Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway |
| US20220383738A1 (en) * | 2021-05-24 | 2022-12-01 | Wuhan University Of Technology | Method for short-term traffic risk prediction of road sections using roadside observation data |
-
2024
- 2024-03-01 CN CN202410231340.9A patent/CN117809458A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508392A (en) * | 2020-12-02 | 2021-03-16 | 云南省交通规划设计研究院有限公司 | Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway |
| US20220383738A1 (en) * | 2021-05-24 | 2022-12-01 | Wuhan University Of Technology | Method for short-term traffic risk prediction of road sections using roadside observation data |
Non-Patent Citations (1)
| Title |
|---|
| 马菲: "基于轨迹数据的快速路交织区交通风险评估", 中国优秀硕士学位论文全文数据库工程科技II辑, 31 January 2024 (2024-01-31), pages 2 - 5 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832225B (en) | Method for constructing driving condition of automobile | |
| Li et al. | Traffic light recognition for complex scene with fusion detections | |
| CN103996287B (en) | A kind of vehicle compulsory based on decision-tree model changes decision-making technique | |
| WO2023065395A1 (en) | Work vehicle detection and tracking method and system | |
| CN112668172B (en) | Following behavior modeling method considering heterogeneity of vehicle type and driving style and model thereof | |
| CN111950488B (en) | Improved Faster-RCNN remote sensing image target detection method | |
| CN114815605A (en) | Automatic driving test case generation method and device, electronic equipment and storage medium | |
| CN114879192A (en) | Decision tree vehicle type classification method based on road side millimeter wave radar and electronic equipment | |
| CN113033899A (en) | Unmanned adjacent vehicle track prediction method | |
| CN116028884A (en) | Prototype network-based vehicle lane change risk assessment method under small sample | |
| CN106056150A (en) | System and method for establishing part division remote damage assessment of different vehicle types based on artificial intelligence random forest method | |
| CN110532904B (en) | Vehicle identification method | |
| CN109615007B (en) | Deep learning network target detection method based on particle filtering | |
| CN112163521A (en) | Vehicle driving behavior identification method, device and equipment | |
| CN117809458A (en) | Real-time assessment method and system for traffic accident risk | |
| CN116361175A (en) | Method for creating test scenes of automatic driving vehicles in different safety domains | |
| CN115860461A (en) | Risk factor evaluation method for traffic conflict of non-motor vehicles at plane intersection | |
| CN112433228B (en) | Multi-laser radar decision-level fusion method and device for pedestrian detection | |
| Xie et al. | Deepcf: A deep feature learning-based car-following model using online ride-hailing trajectory data | |
| CN113065428A (en) | Automatic driving target identification method based on feature selection | |
| CN113313008A (en) | Target and identification tracking method based on YOLOv3 network and mean shift | |
| Ma et al. | Lane change analysis and prediction using mean impact value method and logistic regression model | |
| CN116612642B (en) | Vehicle continuous lane change detection method and electronic equipment | |
| CN112926823B (en) | Intelligent traffic service data detection method and device and electronic equipment | |
| CN106055778A (en) | Remote damage-assessment system and method established based on artificial intelligence for different types of vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |